Dictionary-Driven Ischemia Detection From Cardiac Phase-Resolved Myocardial BOLD MRI at Rest.
Saved in:
| Title: | Dictionary-Driven Ischemia Detection From Cardiac Phase-Resolved Myocardial BOLD MRI at Rest. |
|---|---|
| Authors: | Bevilacqua, Marco1, Dharmakumar, Rohan2, Tsaftaris, Sotirios A.3 |
| Source: | IEEE Transactions on Medical Imaging. Jan2016, Vol. 35 Issue 1, p282-293. 12p. |
| Subjects: | Ischemia diagnosis, Heart physiology, Magnetic resonance imaging, Error analysis in mathematics, Oxygen in the blood |
| Abstract: | Cardiac Phase-resolved Blood-Oxygen-Level Dependent (CP-BOLD) MRI provides a unique opportunity to image an ongoing ischemia at rest. However, it requires post-processing to evaluate the extent of ischemia. To address this, here we propose an unsupervised ischemia detection (UID) method which relies on the inherent spatio-temporal correlation between oxygenation and wall motion to formalize a joint learning and detection problem based on dictionary decomposition. Considering input data of a single subject, it treats ischemia as an anomaly and iteratively learns dictionaries to represent only normal observations (corresponding to myocardial territories remote to ischemia). Anomaly detection is based on a modified version of One-class Support Vector Machines (OCSVM) to regulate directly the margins by incorporating the dictionary-based representation errors. A measure of ischemic extent (IE) is estimated, reflecting the relative portion of the myocardium affected by ischemia. For visualization purposes an ischemia likelihood map is created by estimating posterior probabilities from the OCSVM outputs, thus obtaining how likely the classification is correct. UID is evaluated on synthetic data and in a 2D CP-BOLD data set from a canine experimental model emulating acute coronary syndromes. Comparing early ischemic territories identified with UID against infarct territories (after several hours of ischemia), we find that IE, as measured by UID, is highly correlated (Pearson’s r=0.84) with respect to infarct size. When advances in automated registration and segmentation of CP-BOLD images and full coverage 3D acquisitions become available, we hope that this method can enable pixel-level assessment of ischemia with this truly non-invasive imaging technique. [ABSTRACT FROM AUTHOR] |
| Copyright of IEEE Transactions on Medical Imaging is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 112077457 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Dictionary-Driven Ischemia Detection From Cardiac Phase-Resolved Myocardial BOLD MRI at Rest. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Bevilacqua%2C+Marco%22">Bevilacqua, Marco</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Dharmakumar%2C+Rohan%22">Dharmakumar, Rohan</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Tsaftaris%2C+Sotirios+A%2E%22">Tsaftaris, Sotirios A.</searchLink><relatesTo>3</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Medical+Imaging%22">IEEE Transactions on Medical Imaging</searchLink>. Jan2016, Vol. 35 Issue 1, p282-293. 12p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Ischemia+diagnosis%22">Ischemia diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22Heart+physiology%22">Heart physiology</searchLink><br /><searchLink fieldCode="DE" term="%22Magnetic+resonance+imaging%22">Magnetic resonance imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Error+analysis+in+mathematics%22">Error analysis in mathematics</searchLink><br /><searchLink fieldCode="DE" term="%22Oxygen+in+the+blood%22">Oxygen in the blood</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Cardiac Phase-resolved Blood-Oxygen-Level Dependent (CP-BOLD) MRI provides a unique opportunity to image an ongoing ischemia at rest. However, it requires post-processing to evaluate the extent of ischemia. To address this, here we propose an unsupervised ischemia detection (UID) method which relies on the inherent spatio-temporal correlation between oxygenation and wall motion to formalize a joint learning and detection problem based on dictionary decomposition. Considering input data of a single subject, it treats ischemia as an anomaly and iteratively learns dictionaries to represent only normal observations (corresponding to myocardial territories remote to ischemia). Anomaly detection is based on a modified version of One-class Support Vector Machines (OCSVM) to regulate directly the margins by incorporating the dictionary-based representation errors. A measure of ischemic extent (IE) is estimated, reflecting the relative portion of the myocardium affected by ischemia. For visualization purposes an ischemia likelihood map is created by estimating posterior probabilities from the OCSVM outputs, thus obtaining how likely the classification is correct. UID is evaluated on synthetic data and in a 2D CP-BOLD data set from a canine experimental model emulating acute coronary syndromes. Comparing early ischemic territories identified with UID against infarct territories (after several hours of ischemia), we find that IE, as measured by UID, is highly correlated (Pearson’s r=0.84) with respect to infarct size. When advances in automated registration and segmentation of CP-BOLD images and full coverage 3D acquisitions become available, we hope that this method can enable pixel-level assessment of ischemia with this truly non-invasive imaging technique. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IEEE Transactions on Medical Imaging is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=112077457 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1109/TMI.2015.2470075 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 12 StartPage: 282 Subjects: – SubjectFull: Ischemia diagnosis Type: general – SubjectFull: Heart physiology Type: general – SubjectFull: Magnetic resonance imaging Type: general – SubjectFull: Error analysis in mathematics Type: general – SubjectFull: Oxygen in the blood Type: general Titles: – TitleFull: Dictionary-Driven Ischemia Detection From Cardiac Phase-Resolved Myocardial BOLD MRI at Rest. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Bevilacqua, Marco – PersonEntity: Name: NameFull: Dharmakumar, Rohan – PersonEntity: Name: NameFull: Tsaftaris, Sotirios A. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Text: Jan2016 Type: published Y: 2016 Identifiers: – Type: issn-print Value: 02780062 Numbering: – Type: volume Value: 35 – Type: issue Value: 1 Titles: – TitleFull: IEEE Transactions on Medical Imaging Type: main |
| ResultId | 1 |
